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

    Neuronpedia

    INDEX
    Explanations

    sing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erialize
    -0.07
    اين
    -0.07
     Snake
    -0.07
    .capitalize
    -0.06
    -power
    -0.06
     descriptive
    -0.06
    assage
    -0.06
     gentleman
    -0.06
     近
    -0.06
    insurance
    -0.06
    POSITIVE LOGITS
     Pharm
    0.07
    Reward
    0.06
    .Password
    0.06
    .StylePriority
    0.06
    .Label
    0.06
    	Application
    0.06
    _DIS
    0.06
    .extra
    0.06
    aday
    0.06
     Nullable
    0.06
    Act Density 0.120%

    No Known Activations