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

    Neuronpedia

    INDEX
    Explanations

    giving advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	B
    -0.07
    Kn
    -0.07
     Kenny
    -0.07
    pink
    -0.06
     milk
    -0.06
    sterreich
    -0.06
    	V
    -0.06
    ssa
    -0.06
     throw
    -0.06
    intros
    -0.06
    POSITIVE LOGITS
     Shall
    0.06
     Да
    0.06
    (\$
    0.06
    (il
    0.06
     RegexOptions
    0.06
    /inet
    0.06
    _dm
    0.06
     ^{°}
    0.06
     demol
    0.06
     アル
    0.06
    Act Density 0.203%

    No Known Activations