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

    Neuronpedia

    INDEX
    Explanations

    Abortion-related texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dados
    -0.07
     управ
    -0.07
    textBox
    -0.06
    inition
    -0.06
    ogonal
    -0.06
    dg
    -0.06
     sorun
    -0.06
    .groupby
    -0.06
    osomes
    -0.06
     خرد
    -0.06
    POSITIVE LOGITS
    inheritdoc
    0.07
    (T
    0.07
    (M
    0.07
    	B
    0.07
     starttime
    0.07
    (B
    0.06
    ymous
    0.06
     ------------------------------------------------------------------------↵
    0.06
    -per
    0.06
     κο
    0.06
    Act Density 0.009%

    No Known Activations