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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prefers
    -0.08
     occupied
    -0.07
     garg
    -0.07
    日期
    -0.06
     prefer
    -0.06
     buffet
    -0.06
     facade
    -0.06
     ş
    -0.06
     receipt
    -0.06
     suppressing
    -0.06
    POSITIVE LOGITS
     دری
    0.06
    lords
    0.06
     ISR
    0.06
    _mC
    0.06
    ΥΡ
    0.06
    ρός
    0.06
    _fps
    0.06
    _RGCTX
    0.06
    _epsilon
    0.06
    broker
    0.06
    Act Density 0.009%

    No Known Activations