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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    banner
    -0.07
    └
    -0.07
     esto
    -0.07
     contrato
    -0.07
    polit
    -0.06
    _USAGE
    -0.06
    Euro
    -0.06
     vous
    -0.06
     Wig
    -0.06
     бути
    -0.06
    POSITIVE LOGITS
    _BOUNDS
    0.07
     Actual
    0.07
     Jal
    0.07
     ill
    0.07
     CLR
    0.07
     astounding
    0.07
     совсем
    0.07
    ill
    0.06
    �
    0.06
     Alphabet
    0.06
    Act Density 0.008%

    No Known Activations