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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     youthful
    -0.07
     앞
    -0.07
    。
↵
    -0.06
    .crm
    -0.06
    편
    -0.06
     Stern
    -0.06
    abic
    -0.06
    .INTEGER
    -0.06
    .↵
    -0.06
    .signup
    -0.06
    POSITIVE LOGITS
    码
    0.08
     tow
    0.07
     Mais
    0.06
    secure
    0.06
    няти
    0.06
     Net
    0.06
     climb
    0.06
     Sussex
    0.06
     wines
    0.06
    utta
    0.06
    Act Density 0.000%

    No Known Activations