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

    Neuronpedia

    INDEX
    Explanations

    Code/data processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     divided
    -0.06
    _ER
    -0.06
     affid
    -0.06
     :",
    -0.06
     rodi
    -0.06
    (usuario
    -0.06
    WillAppear
    -0.06
     +#+
    -0.05
    unctuation
    -0.05
    .NoError
    -0.05
    POSITIVE LOGITS
    การ
    0.08
    654
    0.07
     ballistic
    0.07
    undefined
    0.07
    -eng
    0.07
     concurrently
    0.07
    successfully
    0.07
    "
↵
    0.06
     brace
    0.06
    693
    0.06
    Act Density 0.000%

    No Known Activations