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

    Neuronpedia

    INDEX
    Explanations

    code/mathematics expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Darth
    -0.08
    追究
    -0.07
    Nombre
    -0.06
     pervasive
    -0.06
    蹚
    -0.06
     Europa
    -0.06
    あなたの
    -0.06
    TransparentColor
    -0.06
     Springer
    -0.06
     racism
    -0.06
    POSITIVE LOGITS
    썼
    0.07
    来た
    0.07
    closed
    0.07
     adamant
    0.07
    rtype
    0.07
    였
    0.07
    .Ex
    0.07
    +s
    0.07
    满意的
    0.07
    _HASH
    0.07
    Act Density 0.001%

    No Known Activations