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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	api
    -0.07
    Mail
    -0.07
     mash
    -0.07
    bau
    -0.07
     campos
    -0.07
     Blind
    -0.07
    Rad
    -0.07
    cmd
    -0.07
    Reaction
    -0.07
     Reaction
    -0.06
    POSITIVE LOGITS
    andidate
    0.07
    .magnitude
    0.07
     faiz
    0.07
    vron
    0.06
    _ignore
    0.06
     REGARD
    0.06
     grotes
    0.06
    อน
    0.06
     ngon
    0.06
    효
    0.06
    Act Density 0.000%

    No Known Activations