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

    Neuronpedia

    INDEX
    Explanations

    definitions and writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dims
    -0.08
    _MINUS
    -0.07
     중요
    -0.07
    timestamp
    -0.07
     เพราะ
    -0.07
    程
    -0.07
    wicklung
    -0.07
    upaten
    -0.07
     giorni
    -0.07
    ieren
    -0.07
    POSITIVE LOGITS
     Perfect
    0.07
     spider
    0.07
    mag
    0.07
    odom
    0.07
     presumably
    0.06
     INIT
    0.06
     Pure
    0.06
     _
↵
    0.06
    now
    0.06
     Ob
    0.06
    Act Density 0.007%

    No Known Activations