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

    Neuronpedia

    INDEX
    Explanations

    US states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isations
    -0.08
     permutations
    -0.07
    え
    -0.07
     occured
    -0.07
    �
    -0.07
    addPreferredGap
    -0.07
    иш
    -0.07
     breaks
    -0.06
    运营商
    -0.06
     الأطفال
    -0.06
    POSITIVE LOGITS
    roma
    0.07
     rhetorical
    0.07
    -solid
    0.07
    adopt
    0.07
    ŏ
    0.06
    motor
    0.06
    -region
    0.06
     secretive
    0.06
     Martha
    0.06
    thermal
    0.06
    Act Density 0.068%

    No Known Activations