Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    military branches

    np_max-act · gemini-2.0-flash

    The neuron detects references to naval forces (e.g. mentions of “Navy,” “naval,” fleet, ship classes, and related maritime military terms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    <char
    -0.08
    ثر
    -0.07
     regulators
    -0.07
     regulator
    -0.06
    works
    -0.06
    13
    -0.06
    .closest
    -0.06
     COLORS
    -0.06
     pans
    -0.06
     streams
    -0.06
    POSITIVE LOGITS
     elaborate
    0.07
    abr
    0.06
    OCUMENT
    0.06
     TLabel
    0.06
    Derived
    0.06
     confined
    0.06
     ayud
    0.06
     Ngành
    0.06
     Β
    0.06
    ;}↵
    0.06
    Act Density 0.015%

    No Known Activations