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

    Neuronpedia

    INDEX
    Explanations

    Barber

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nuts
    -0.07
    .float
    -0.07
     jak
    -0.07
    _levels
    -0.07
    /list
    -0.06
    ая
    -0.06
    _assoc
    -0.06
     slowing
    -0.06
    ô
    -0.06
     stress
    -0.06
    POSITIVE LOGITS
     Barber
    0.08
    /sql
    0.06
     Esther
    0.06
     аналіз
    0.06
     amber
    0.06
    ")))↵
    0.06
    LDAP
    0.06
    -proof
    0.06
    완
    0.06
     vampire
    0.06
    Act Density 0.001%

    No Known Activations