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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     communication
    -0.07
     arbitration
    -0.06
     mixture
    -0.06
    แข
    -0.06
     الس
    -0.06
     undercut
    -0.06
     tact
    -0.06
     impact
    -0.06
    .RESET
    -0.06
    描述
    -0.06
    POSITIVE LOGITS
    (QStringLiteral
    0.07
    ولوژی
    0.07
    _THAN
    0.07
    stashop
    0.06
     procedural
    0.06
    少年
    0.06
    لاث
    0.06
     Hàn
    0.06
    USB
    0.06
     Accounts
    0.06
    Act Density 0.001%

    No Known Activations