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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     необходимости
    -0.07
    licenses
    -0.07
     manslaughter
    -0.07
    enção
    -0.07
    本赛季
    -0.07
    ഫ
    -0.06
    _declaration
    -0.06
    官
    -0.06
     granting
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     LGBTQ
    0.08
    	raw
    0.07
     ART
    0.07
     uniquely
    0.07
    ⾊
    0.07
    正確
    0.07
    igit
    0.07
    last
    0.07
    .last
    0.07
    lm
    0.06
    Act Density 0.040%

    No Known Activations