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

    Neuronpedia

    INDEX
    Explanations

    between

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cred
    -0.07
    ,tr
    -0.07
     digest
    -0.07
    ocale
    -0.07
    _raises
    -0.06
     Mime
    -0.06
     morale
    -0.06
     intro
    -0.06
     Skill
    -0.06
     Rise
    -0.06
    POSITIVE LOGITS
     Between
    0.08
     between
    0.08
    between
    0.07
    Between
    0.07
    чів
    0.06
     якої
    0.06
    ミ
    0.06
    elian
    0.06
    ника
    0.06
    訴
    0.06
    Act Density 0.010%

    No Known Activations