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

    Neuronpedia

    INDEX
    Explanations

    Code configuration files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amientos
    -0.07
     DEVELO
    -0.07
    erreur
    -0.07
    =$_
    -0.06
    org
    -0.06
    userManager
    -0.06
    .year
    -0.06
    xor
    -0.06
     psychologists
    -0.06
    液
    -0.06
    POSITIVE LOGITS
     RID
    0.06
    _loader
    0.06
    .ColumnName
    0.06
    征
    0.06
    akat
    0.05
     hex
    0.05
    TERM
    0.05
    .top
    0.05
    �n
    0.05
     соот
    0.05
    Act Density 0.002%

    No Known Activations