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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ั่
    -0.07
     �
    -0.07
    ă
    -0.07
     preferences
    -0.07
    rewrite
    -0.07
    .course
    -0.07
    (P
    -0.06
     Hire
    -0.06
    _animation
    -0.06
     predetermined
    -0.06
    POSITIVE LOGITS
     whole
    0.06
    (JNIEnv
    0.06
     firefox
    0.06
    lej
    0.06
    .Quad
    0.06
     xe
    0.06
     ビ
    0.06
    ома
    0.06
     azal
    0.06
     지금
    0.06
    Act Density 0.052%

    No Known Activations