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

    Neuronpedia

    INDEX
    Explanations

    preference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _into
    -0.07
    lando
    -0.06
     kneeling
    -0.06
     excit
    -0.06
     steak
    -0.06
    oples
    -0.06
     overly
    -0.06
     مبار
    -0.06
     cél
    -0.06
     лож
    -0.06
    POSITIVE LOGITS
    ↵↵↵↵↵↵
    0.09
    잖
    0.07
    _FMT
    0.07
    edir
    0.06
     displayName
    0.06
     utilized
    0.06
     Syntax
    0.06
    ENAME
    0.06
    ARED
    0.06
    credited
    0.06
    Act Density 0.022%

    No Known Activations