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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ませ
    -0.07
    蛲
    -0.07
    头疼
    -0.07
    .plus
    -0.07
    ]-'
    -0.07
    🤸
    -0.07
    憷
    -0.07
    ведущ
    -0.07
    �
    -0.07
    ItemSelectedListener
    -0.07
    POSITIVE LOGITS
    form
    0.08
    ificates
    0.07
    aria
    0.07
     Kim
    0.07
    perm
    0.07
    mania
    0.07
     Qu
    0.07
     Jerome
    0.07
     conformity
    0.07
     Auth
    0.07
    Act Density 0.001%

    No Known Activations