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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lav
    -0.07
    Gov
    -0.07
    Large
    -0.06
    .Side
    -0.06
    _msg
    -0.06
     elementos
    -0.06
     Patty
    -0.06
    .Aggressive
    -0.06
    mongodb
    -0.06
     chiế
    -0.06
    POSITIVE LOGITS
     here
    0.10
     aqui
    0.08
    _legal
    0.07
     ec
    0.06
     работать
    0.06
    έρει
    0.06
    故
    0.06
    ('.')[
    0.06
    ACL
    0.06
    effects
    0.06
    Act Density 0.022%

    No Known Activations