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

    Neuronpedia

    INDEX
    Explanations

    masks symptoms or underlying causes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cape
    0.46
     selection
    0.43
     restriction
    0.42
     રહે
    0.42
    selection
    0.42
    querysearch
    0.42
     throwIf
    0.42
    wallepics
    0.42
    ガル
    0.41
    ப்பட்டி
    0.41
    POSITIVE LOGITS
     أن
    0.49
    ↵
    0.44
    以
    0.44
     irr
    0.43
     by
    0.41
    ein
    0.41
     أنه
    0.41
     BOR
    0.41
    ]$.
    0.41
    '
    0.40
    Act Density 0.002%

    No Known Activations