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

    Neuronpedia

    INDEX
    Explanations

    Quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    假
    -0.07
    Allocator
    -0.06
    >a
    -0.06
     Babies
    -0.06
    _Pin
    -0.06
    ROKE
    -0.06
    oma
    -0.06
     Satan
    -0.06
     False
    -0.06
     epidemic
    -0.06
    POSITIVE LOGITS
    ßerdem
    0.07
    agens
    0.07
     steht
    0.07
     counsel
    0.06
    _jump
    0.06
     eigentlich
    0.06
     primal
    0.06
    .-
    0.06
     bisher
    0.06
     central
    0.06
    Act Density 0.091%

    No Known Activations