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

    Neuronpedia

    INDEX
    Explanations

    impossible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _slave
    -0.09
    职
    -0.08
    Transmission
    -0.08
    Kes
    -0.08
    备用
    -0.08
    _lang
    -0.07
    ränkt
    -0.07
    /users
    -0.07
     chaos
    -0.07
    shme
    -0.07
    POSITIVE LOGITS
     impossible
    0.09
     architectures
    0.09
     strane
    0.09
     Bhutan
    0.08
     Impossible
    0.08
    architecture
    0.08
     imposible
    0.08
     improb
    0.08
     Türki
    0.08
     disappears
    0.08
    Act Density 0.005%

    No Known Activations