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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Positive
    -0.07
    :"-"`↵
    -0.06
    .Raycast
    -0.06
     Appropri
    -0.06
     GSM
    -0.06
     Fathers
    -0.06
     Quinn
    -0.06
     swings
    -0.06
     ')';↵
    -0.06
    ausal
    -0.06
    POSITIVE LOGITS
     hw
    0.07
    eeee
    0.07
    onation
    0.06
     al
    0.06
    ,Z
    0.06
     exception
    0.06
    .O
    0.06
     pi
    0.06
    Pro
    0.06
    ,H
    0.06
    Act Density 0.000%

    No Known Activations