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
     <<
    -0.07
     ні
    -0.06
     medieval
    -0.06
     bilateral
    -0.06
    REDENTIAL
    -0.06
    普
    -0.06
    qq
    -0.06
     boycott
    -0.06
     Cath
    -0.06
     BaseActivity
    -0.06
    POSITIVE LOGITS
     axiom
    0.07
    okableCall
    0.07
    GLfloat
    0.07
     関連
    0.07
     plugin
    0.07
    ,json
    0.06
     graduating
    0.06
     могла
    0.06
     macht
    0.06
    .↵↵
    0.06
    Act Density 0.004%

    No Known Activations