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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    
    -0.07
     crossover
    -0.07
     withholding
    -0.06
     jiný
    -0.06
    ophy
    -0.06
    ीद
    -0.06
    	dd
    -0.06
    _Color
    -0.06
    Password
    -0.06
     Instagram
    -0.06
    POSITIVE LOGITS
     μεγά
    0.06
     Şubat
    0.06
    pickle
    0.06
     Koch
    0.06
    .Before
    0.06
    vocab
    0.05
    ечно
    0.05
     kleine
    0.05
     provoc
    0.05
     bekan
    0.05
    Act Density 0.000%

    No Known Activations