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

    Neuronpedia

    INDEX
    Explanations

    security considerations and business side

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veya
    0.42
     அல்லது
    0.41
    别
    0.38
    IMENTAL
    0.37
     d
    0.37
     couleurs
    0.36
     '('
    0.36
     marcos
    0.36
     '__
    0.36
     \
    0.36
    POSITIVE LOGITS
    Tabpage
    0.45
    Renew
    0.44
    ckså
    0.44
    CallSettings
    0.44
    Anche
    0.44
     advocating
    0.43
     tapered
    0.42
    titleMargin
    0.42
    nilvadipine
    0.42
    antaranya
    0.42
    Act Density 0.004%

    No Known Activations