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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .pen
    -0.07
     possesses
    -0.07
    登
    -0.06
    page
    -0.06
    '^
    -0.06
    㠓
    -0.06
    小腿
    -0.06
    uddenly
    -0.06
     advertising
    -0.06
    ⍣
    -0.06
    POSITIVE LOGITS
    gement
    0.08
    структур
    0.07
    mort
    0.07
    eration
    0.07
    져
    0.07
     SERVER
    0.07
     troubled
    0.07
     suite
    0.07
     recruiter
    0.07
    �
    0.07
    Act Density 0.000%

    No Known Activations