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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PARAMETERS
    -0.07
    .RowCount
    -0.07
    ραβ
    -0.07
     Contributions
    -0.07
     İst
    -0.07
     Rew
    -0.07
    .inventory
    -0.07
    nesday
    -0.07
    yslu
    -0.06
     Kunden
    -0.06
    POSITIVE LOGITS
    超过
    0.08
    ddit
    0.07
    .sap
    0.06
    igan
    0.06
    916
    0.06
    Receiver
    0.06
    _FM
    0.06
    僅
    0.06
    ωμα
    0.05
    uly
    0.05
    Act Density 0.004%

    No Known Activations