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

    Neuronpedia

    INDEX
    Explanations

    logical entailment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    review
    -0.06
     violet
    -0.06
     responding
    -0.06
    inema
    -0.06
    design
    -0.06
     Cube
    -0.06
    >M
    -0.06
     从
    -0.06
     Với
    -0.06
    ميم
    -0.06
    POSITIVE LOGITS
    annotate
    0.07
    .setProgress
    0.06
    さま
    0.06
    _logout
    0.06
     entail
    0.06
     copyrighted
    0.06
    (bot
    0.06
    _EV
    0.06
     queryset
    0.06
    ็จ
    0.06
    Act Density 0.001%

    No Known Activations