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

    Neuronpedia

    INDEX
    Explanations

    Smith

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ecký
    -0.07
     Quý
    -0.07
     Gavin
    -0.07
     Gala
    -0.07
     κάθε
    -0.07
    curity
    -0.06
     Králové
    -0.06
    .toJSONString
    -0.06
     Tracy
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    550
    0.09
    ls
    0.08
    .commit
    0.08
    531
    0.07
     Jones
    0.07
    Command
    0.07
     hold
    0.07
    MT
    0.07
     capitalist
    0.07
     bat
    0.07
    Act Density 0.036%

    No Known Activations