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

    Neuronpedia

    INDEX
    Explanations

    If

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sentencing
    -0.07
     Enhancement
    -0.07
    heartbeat
    -0.06
     سی
    -0.06
    .hover
    -0.06
     jac
    -0.06
    resenter
    -0.06
     continua
    -0.06
     Clo
    -0.06
     trench
    -0.06
    POSITIVE LOGITS
    �
    0.06
     ук
    0.06
     Bool
    0.06
     stalled
    0.06
    ,ID
    0.06
     křes
    0.06
    алів
    0.06
     магаз
    0.06
    .getPort
    0.06
     archit
    0.06
    Act Density 0.020%

    No Known Activations