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

    Neuronpedia

    INDEX
    Explanations

    Apple related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    似乎
    -0.07
    VM
    -0.07
    絵
    -0.07
    Exclusive
    -0.06
    orgetown
    -0.06
     설명
    -0.06
    prefer
    -0.06
     doporuč
    -0.06
    Lambda
    -0.06
    conom
    -0.06
    POSITIVE LOGITS
    	tag
    0.07
    .bp
    0.07
    _LOOP
    0.06
    apes
    0.06
     pojištění
    0.06
     dopl
    0.06
     Gerry
    0.06
     geri
    0.06
     تشکیل
    0.06
    &action
    0.06
    Act Density 0.011%

    No Known Activations