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

    Neuronpedia

    INDEX
    Explanations

    peer review

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Domain
    -0.06
     extremism
    -0.06
     meanwhile
    -0.06
     gentlemen
    -0.06
    .jd
    -0.06
     PhoneNumber
    -0.06
    DXVECTOR
    -0.06
     Григор
    -0.05
    938
    -0.05
     ב
    -0.05
    POSITIVE LOGITS
     существ
    0.07
     ruling
    0.07
    лись
    0.06
     emphasized
    0.06
    TION
    0.06
     intersection
    0.06
     Literal
    0.06
    .Actor
    0.06
    FromBody
    0.06
     Animal
    0.06
    Act Density 0.007%

    No Known Activations