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

    Neuronpedia

    INDEX
    Explanations

    Hypothetical situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cue
    -0.07
    นอ
    -0.06
    Driving
    -0.06
    TemplateName
    -0.06
    isters
    -0.06
    bern
    -0.06
     warranties
    -0.06
    abouts
    -0.06
    ErrMsg
    -0.06
     yacc
    -0.06
    POSITIVE LOGITS
     nam
    0.08
    quia
    0.07
    684
    0.07
     pys
    0.07
    texto
    0.07
    IALIZED
    0.07
     phys
    0.06
     普通
    0.06
    去了
    0.06
    =\'
    0.06
    Act Density 0.005%

    No Known Activations