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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bl
    -0.08
    ccion
    -0.08
     ов
    -0.07
    YC
    -0.07
     teor
    -0.07
     �
    -0.07
    TOR
    -0.06
    CESS
    -0.06
     wordpress
    -0.06
    PKG
    -0.06
    POSITIVE LOGITS
    643
    0.06
     individually
    0.06
     cerr
    0.06
    \Auth
    0.06
     heat
    0.06
    .createUser
    0.06
    ToSelector
    0.06
    ^(
    0.06
    (ir
    0.05
     executable
    0.05
    Act Density 0.001%

    No Known Activations