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

    Neuronpedia

    INDEX
    Explanations

    about access and control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ).
    0.49
    Ա
    0.46
    𝗿
    0.46
    aphylococcus
    0.45
     დ
    0.45
     हारे
    0.44
    ):
    0.43
    rà
    0.43
     llevará
    0.43
     मिलेगा
    0.43
    POSITIVE LOGITS
     teknik
    0.46
    Gravestone
    0.43
     Shrimp
    0.41
    Quota
    0.41
     builder
    0.40
    一台
    0.40
     Compressor
    0.40
     looked
    0.40
     Camera
    0.40
     Coffee
    0.40
    Act Density 0.002%

    No Known Activations