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

    Neuronpedia

    INDEX
    Explanations

    Sherlock Holmes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    수의
    -0.08
     sure
    -0.07
    据
    -0.07
    ื่
    -0.07
     вклад
    -0.06
    adh
    -0.06
     event
    -0.06
    逆
    -0.06
     diapers
    -0.06
     غیر
    -0.06
    POSITIVE LOGITS
    Echo
    0.07
     akşam
    0.06
    0.06
    raw
    0.06
    حن
    0.06
    '){
↵
    0.06
    emble
    0.06
    0.06
     architect
    0.06
     melodies
    0.06
    Act Density 0.040%

    No Known Activations