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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ็บ
    -0.07
    Plus
    -0.07
     barrier
    -0.07
     axios
    -0.07
    披
    -0.06
     אני
    -0.06
    少
    -0.06
     pave
    -0.06
    .Map
    -0.06
    ifiable
    -0.06
    POSITIVE LOGITS
    핟
    0.08
    (question
    0.07
    쫘
    0.07
     Charity
    0.07
    𝐓
    0.06
     בקלות
    0.06
    ਜ
    0.06
    想去
    0.06
     translators
    0.06
     Hank
    0.06
    Act Density 0.020%

    No Known Activations