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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cadastro
    -0.07
    avings
    -0.07
     -->↵↵
    -0.07
    _embeddings
    -0.07
     مخروط
    -0.06
    .setVisibility
    -0.06
    -drive
    -0.06
    developers
    -0.06
    ійської
    -0.06
     Cell
    -0.06
    POSITIVE LOGITS
     actual
    0.06
     INSTALL
    0.06
     strSQL
    0.06
     kicked
    0.06
     тоже
    0.06
     sexually
    0.06
    iyor
    0.06
     alternatively
    0.06
     external
    0.06
    	msg
    0.06
    Act Density 0.049%

    No Known Activations