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

    Neuronpedia

    INDEX
    Explanations

    Non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    еры
    -0.08
    memberof
    -0.07
    .add
    -0.07
     SUBJECT
    -0.07
    ники
    -0.07
    Receive
    -0.07
    .ONE
    -0.07
    fiber
    -0.07
    Sources
    -0.06
    _dataset
    -0.06
    POSITIVE LOGITS
    กร
    0.07
     exercitation
    0.06
    面
    0.06
     rebell
    0.06
    GetProcAddress
    0.06
     dosp
    0.06
     regain
    0.06
    .getDate
    0.06
     campos
    0.05
    標準
    0.05
    Act Density 0.039%

    No Known Activations