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

    Neuronpedia

    INDEX
    Explanations

    scientific research funding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myself
    -0.07
     meth
    -0.07
     כש
    -0.07
    iii
    -0.06
     Meth
    -0.06
    ón
    -0.06
     Lace
    -0.06
    rés
    -0.06
    ᅭ
    -0.06
    уще
    -0.06
    POSITIVE LOGITS
     Plugins
    0.09
    CID
    0.07
    _HELP
    0.07
    חול
    0.07
     humor
    0.07
    rients
    0.07
     insults
    0.07
     resources
    0.07
    于一体的
    0.07
     unsett
    0.07
    Act Density 0.010%

    No Known Activations