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

    Neuronpedia

    INDEX
    Explanations

    grammars and productions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "#
    -0.07
     IX
    -0.06
     Cec
    -0.06
     }//
    -0.06
     delve
    -0.06
     Newton
    -0.06
     bags
    -0.06
     BDS
    -0.06
     Assange
    -0.06
     ціл
    -0.06
    POSITIVE LOGITS
     відом
    0.07
     volcano
    0.07
    ię
    0.07
    cased
    0.06
    heat
    0.06
    riet
    0.06
    teş
    0.06
     zamanda
    0.06
     bara
    0.06
    lid
    0.06
    Act Density 0.005%

    No Known Activations