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

    Neuronpedia

    INDEX
    Explanations

    Intellectual property, multimedia analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cookbook
    0.43
    醃
    0.42
     emblematic
    0.42
    нци
    0.41
    არა
    0.41
     plateforme
    0.40
     toothbrush
    0.40
     lego
    0.39
    StubCompat
    0.39
     marshmallow
    0.39
    POSITIVE LOGITS
    VP
    0.43
    restart
    0.42
    "+"
    0.38
    bigvee
    0.38
    TC
    0.37
    Dynamic
    0.36
    到
    0.36
    <s>
    0.35
     عاملين
    0.35
    begin
    0.34
    Act Density 0.000%

    No Known Activations