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

    Neuronpedia

    INDEX
    Explanations

    Preventative advice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nodo
    -0.07
    mPid
    -0.07
    쐬
    -0.06
     실
    -0.06
    getNum
    -0.06
    䨰
    -0.06
    羽
    -0.06
     בדי
    -0.06
    מוסר
    -0.06
    cbc
    -0.06
    POSITIVE LOGITS
    กระทรว
    0.08
    _convert
    0.07
     br
    0.07
     participates
    0.07
    Patrick
    0.07
     trajectories
    0.07
     profiles
    0.07
     directives
    0.07
     utmost
    0.06
     routing
    0.06
    Act Density 0.031%

    No Known Activations