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

    Neuronpedia

    INDEX
    Explanations

    less

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خدا
    -0.07
     Kyoto
    -0.07
     victories
    -0.07
     examination
    -0.07
    Modificar
    -0.07
    **,
    -0.06
     Auditor
    -0.06
    _,
    -0.06
    aporation
    -0.06
    -ag
    -0.06
    POSITIVE LOGITS
    less
    0.15
    LESS
    0.11
    ess
    0.09
    -less
    0.08
    close
    0.08
    loss
    0.08
     GLES
    0.08
     homeless
    0.08
    MESS
    0.08
     Less
    0.08
    Act Density 0.015%

    No Known Activations