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

    Neuronpedia

    INDEX
    Explanations

    costs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     color
    -0.07
    ă
    -0.07
     adjustable
    -0.07
     أكد
    -0.07
     vestib
    -0.06
    ()=>
    -0.06
     cellphone
    -0.06
    _UD
    -0.06
    argument
    -0.06
    POSITIVE LOGITS
     conglomer
    0.07
     dudes
    0.07
    DDL
    0.07
     FUCK
    0.07
    悅
    0.07
    .Helper
    0.07
    Defs
    0.07
     Rangers
    0.07
     DIV
    0.07
    ʚ
    0.07
    Act Density 0.087%

    No Known Activations