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

    Neuronpedia

    INDEX
    Explanations

    say "to/enough"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KeyType
    -0.08
    ㄇ
    -0.08
    asant
    -0.07
     vt
    -0.07
    .yaml
    -0.07
    oscope
    -0.07
    /dc
    -0.07
     provoke
    -0.07
     ammonia
    -0.07
    _medium
    -0.07
    POSITIVE LOGITS
    >'↵
    0.07
    aptive
    0.07
     администраци
    0.07
     field
    0.07
    חמישי
    0.07
     environment
    0.07
     Berlin
    0.06
    >,↵
    0.06
     platform
    0.06
    칟
    0.06
    Act Density 0.022%

    No Known Activations