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

    Neuronpedia

    INDEX
    Explanations

    the,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -M
    -0.06
    蘇
    -0.06
    ookeeper
    -0.06
    MS
    -0.06
     pioneering
    -0.06
     sensit
    -0.06
    -R
    -0.06
    ーリ
    -0.06
     fond
    -0.06
     ettiği
    -0.06
    POSITIVE LOGITS
    "name
    0.08
    88
    0.07
    ()."
    0.07
    candidate
    0.06
    ][$
    0.06
     आग
    0.06
    ätzlich
    0.06
     。↵
    0.06
    *',
    0.06
    INUE
    0.06
    Act Density 0.064%

    No Known Activations