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

    Neuronpedia

    INDEX
    Explanations

    lesser

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bitten
    -0.07
     того
    -0.07
    uppy
    -0.07
    (ArrayList
    -0.07
     loose
    -0.07
    isen
    -0.06
    _look
    -0.06
    //
↵
↵
    -0.06
     �
    -0.06
    ///
↵
    -0.06
    POSITIVE LOGITS
    τας
    0.08
    ctrine
    0.06
     paciente
    0.06
    .tip
    0.06
     هستند
    0.06
    购买
    0.06
     bats
    0.05
    .=
    0.05
     nimi
    0.05
     zorun
    0.05
    Act Density 0.025%

    No Known Activations