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

    Neuronpedia

    INDEX
    Explanations

    on/to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abilia
    -0.06
     forth
    -0.06
    珠
    -0.06
    琳
    -0.06
    ैन
    -0.06
     Streams
    -0.06
    .jboss
    -0.06
     foolish
    -0.06
    κα
    -0.06
     injunction
    -0.06
    POSITIVE LOGITS
     života
    0.06
     runtime
    0.06
    眉
    0.06
    being
    0.06
     caf
    0.06
    物理
    0.06
     republice
    0.06
    .zeros
    0.06
    ości
    0.06
     showing
    0.06
    Act Density 0.044%

    No Known Activations