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

    Neuronpedia

    INDEX
    Explanations

    Variable names/keys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Inv
    -0.07
    _xpath
    -0.07
     أحمد
    -0.07
     infield
    -0.07
    =username
    -0.07
     יוסף
    -0.07
    _MASTER
    -0.07
     Suarez
    -0.07
    amba
    -0.06
    ℃
    -0.06
    POSITIVE LOGITS
    	y
    0.08
    は
    0.07
     và
    0.07
     visto
    0.07
    .G
    0.07
     hil
    0.06
     E
    0.06
    >,
    0.06
     Что
    0.06
    Debugger
    0.06
    Act Density 0.048%

    No Known Activations