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

    Neuronpedia

    INDEX
    Explanations

    Code and task workflows

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dense
    -0.07
    -0.07
    Responsive
    -0.07
     услуг
    -0.06
    perator
    -0.06
    decision
    -0.06
    esen
    -0.06
    覺
    -0.06
    iod
    -0.06
    ि,
    -0.06
    POSITIVE LOGITS
    _CLASSES
    0.06
    deb
    0.06
    tok
    0.06
    της
    0.06
    สมาช
    0.06
    buttonShape
    0.06
    �
    0.06
     CHAR
    0.06
     Optical
    0.06
     Charset
    0.05
    Act Density 0.021%

    No Known Activations