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

    Neuronpedia

    INDEX
    Explanations

    visual forms and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vanwege
    0.38
    嬗
    0.37
    াকিব
    0.36
    🧢
    0.36
    niego
    0.36
    WebV
    0.35
     డౌ
    0.34
    aredPreferences
    0.34
    مارات
    0.34
    ServiceGroupID
    0.34
    POSITIVE LOGITS
    0.38
    array
    0.37
     alert
    0.34
    Large
    0.34
     $\
    0.34
    Log
    0.34
    Flat
    0.34
     a
    0.33
    Go
    0.33
     Bass
    0.33
    Act Density 0.000%

    No Known Activations