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

    Neuronpedia

    INDEX
    Explanations

    idea

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Credentials
    -0.07
    �
    -0.07
    alıdır
    -0.07
     adds
    -0.06
     Execution
    -0.06
     Went
    -0.06
    _web
    -0.06
    久
    -0.06
     Adds
    -0.06
     werk
    -0.06
    POSITIVE LOGITS
    حل
    0.07
    skins
    0.07
    Normals
    0.06
     chuck
    0.06
     abre
    0.06
     Particularly
    0.06
     MSR
    0.06
    +self
    0.06
     escri
    0.06
     přiv
    0.06
    Act Density 0.020%

    No Known Activations