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

    Neuronpedia

    INDEX
    Explanations

    placement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Assembler
    -0.07
    _priv
    -0.07
    _means
    -0.07
    Constructor
    -0.07
     Direction
    -0.06
     Josef
    -0.06
     Prescott
    -0.06
    Loan
    -0.06
     analyzing
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    .did
    0.07
    rvé
    0.06
     Budd
    0.06
     hoch
    0.06
     edad
    0.06
    	long
    0.06
    IGNED
    0.06
    ньому
    0.06
    atisfaction
    0.06
     autoComplete
    0.06
    Act Density 0.029%

    No Known Activations