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

    Neuronpedia

    INDEX
    Explanations

    echo

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     кажется
    -0.07
     prognosis
    -0.07
     checkboxes
    -0.07
    处在
    -0.07
     חיובי
    -0.07
     delimited
    -0.07
    овым
    -0.07
    ricanes
    -0.06
     işlemleri
    -0.06
    .kr
    -0.06
    POSITIVE LOGITS
     Allies
    0.08
    ซ
    0.07
     Episode
    0.07
    ह
    0.07
    arm
    0.07
    sim
    0.07
    annon
    0.07
     없
    0.07
    adam
    0.07
    滤
    0.07
    Act Density 0.082%

    No Known Activations