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

    Neuronpedia

    INDEX
    Explanations

    lunch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TK
    -0.07
    ulares
    -0.07
    <label
    -0.06
    Padding
    -0.06
    forest
    -0.06
    Falsy
    -0.06
     بخش
    -0.06
    اپیم
    -0.06
    .parent
    -0.06
     langu
    -0.06
    POSITIVE LOGITS
    は
    0.07
     Meditation
    0.07
     حيث
    0.07
    homme
    0.06
    note
    0.06
    ands
    0.06
     [_
    0.06
     *}
    0.06
     ]
↵
    0.06
    fans
    0.06
    Act Density 0.017%

    No Known Activations