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

    Neuronpedia

    INDEX
    Explanations

    version

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    54
    -0.06
     nostra
    -0.06
    Look
    -0.06
     chaotic
    -0.06
    45
    -0.06
     pole
    -0.06
     Sat
    -0.06
    chestra
    -0.06
     pop
    -0.06
     Look
    -0.06
    POSITIVE LOGITS
     versions
    0.11
     version
    0.11
     Version
    0.09
    .version
    0.09
    version
    0.08
    Version
    0.08
    역
    0.08
    ver
    0.08
    종
    0.08
    �
    0.08
    Act Density 0.035%

    No Known Activations