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

    Neuronpedia

    INDEX
    Explanations

    clip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (inst
    -0.07
     waterfront
    -0.07
    _NULL
    -0.07
    "F
    -0.07
     sustained
    -0.07
     fault
    -0.06
    (words
    -0.06
    Selection
    -0.06
    _AX
    -0.06
    Node
    -0.06
    POSITIVE LOGITS
     locker
    0.08
    нима
    0.07
    region
    0.07
    undai
    0.06
    所以
    0.06
     UIStoryboardSegue
    0.06
    ività
    0.06
     "*
    0.06
    .dtd
    0.06
    DE
    0.06
    Act Density 0.004%

    No Known Activations