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

    Neuronpedia

    INDEX
    Explanations

    conducted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aus
    -0.07
    -series
    -0.06
    raphic
    -0.06
     Dies
    -0.06
     deserved
    -0.06
     Barry
    -0.05
     갤
    -0.05
     INCLUDED
    -0.05
    'était
    -0.05
     khăn
    -0.05
    POSITIVE LOGITS
    Capture
    0.07
    Downloading
    0.07
     repe
    0.07
     lever
    0.07
    -position
    0.07
     lamp
    0.06
     confirm
    0.06
    _escape
    0.06
     implic
    0.06
     gerekir
    0.06
    Act Density 0.005%

    No Known Activations