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

    Neuronpedia

    INDEX
    Explanations

    -language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ds
    -0.08
    ˶
    -0.07
     הבא
    -0.07
    娛
    -0.07
    幼稚
    -0.07
     Gret
    -0.07
     DS
    -0.07
    诱人
    -0.07
     mük
    -0.07
     deserved
    -0.07
    POSITIVE LOGITS
    _vert
    0.07
    unicorn
    0.07
    -password
    0.06
     lev
    0.06
    vero
    0.06
     intercept
    0.06
    protein
    0.06
     standpoint
    0.06
     ineff
    0.06
    (UnityEngine
    0.06
    Act Density 0.000%

    No Known Activations