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

    Neuronpedia

    INDEX
    Explanations

    surnames and academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nums
    0.56
     Placeholder
    0.55
     Automatically
    0.54
     SOAP
    0.54
     fallback
    0.54
     webhook
    0.53
     cog
    0.53
     Paramount
    0.53
     lock
    0.51
     core
    0.51
    POSITIVE LOGITS
    opoulos
    0.94
    觟
    0.85
    ková
    0.80
    emberg
    0.77
    kovi
    0.76
    anski
    0.76
    等人
    0.75
    žič
    0.73
    insk
    0.72
    ansky
    0.72
    Act Density 0.031%

    No Known Activations