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

    Neuronpedia

    INDEX
    Explanations

    technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BindView
    -0.07
    ממוצע
    -0.07
    |RF
    -0.07
    _CHAIN
    -0.07
    esign
    -0.06
    狴
    -0.06
    膘
    -0.06
    .Throws
    -0.06
    登上
    -0.06
     coax
    -0.06
    POSITIVE LOGITS
    (shader
    0.08
    AxisAlignment
    0.07
    Listener
    0.07
     spoil
    0.07
    ある
    0.07
     mana
    0.07
    	ct
    0.07
     مباشرة
    0.06
    earned
    0.06
     danger
    0.06
    Act Density 0.021%

    No Known Activations