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

    Neuronpedia

    INDEX
    Explanations

    expression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    submitted
    -0.07
    श
    -0.07
    リア
    -0.07
    .Convert
    -0.07
     Dialogue
    -0.07
    =function
    -0.07
    提
    -0.06
     dol
    -0.06
    産
    -0.06
     年
    -0.06
    POSITIVE LOGITS
     }]
    0.07
    iphertext
    0.07
    ,j
    0.06
     bru
    0.06
    .codigo
    0.06
     Troll
    0.06
    cliffe
    0.06
    qué
    0.06
     mojo
    0.06
     yasak
    0.06
    Act Density 0.009%

    No Known Activations