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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     devoid
    -0.08
     thật
    -0.07
    -make
    -0.07
     complic
    -0.07
     experimented
    -0.07
     UIS
    -0.07
     Automobile
    -0.07
     insult
    -0.07
    urve
    -0.07
     pumped
    -0.07
    POSITIVE LOGITS
    �
    0.07
    Rule
    0.07
    FK
    0.07
    zon
    0.07
    Oct
    0.07
     Welfare
    0.07
    ʆ
    0.07
    roy
    0.07
    챔
    0.06
     Gesch
    0.06
    Act Density 0.011%

    No Known Activations