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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Destroy
    -0.07
    _schema
    -0.07
    φυ
    -0.06
     webs
    -0.06
    ("./
    -0.06
     enviado
    -0.06
     aproxim
    -0.06
     SEN
    -0.06
    _k
    -0.06
    _literal
    -0.06
    POSITIVE LOGITS
     تخصص
    0.07
     उनक
    0.06
    っぱい
    0.06
    (Process
    0.06
    domains
    0.06
    _flg
    0.06
    -Trump
    0.06
    (flags
    0.06
     unfortunately
    0.06
     電
    0.06
    Act Density 0.001%

    No Known Activations