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

    Neuronpedia

    INDEX
    Explanations

    exercise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     single
    -0.08
    grass
    -0.08
    _shot
    -0.07
     Sally
    -0.07
    IVAL
    -0.07
    ongs
    -0.07
     creek
    -0.07
    .sprite
    -0.07
     meer
    -0.07
    <src
    -0.06
    POSITIVE LOGITS
    -important
    0.06
    _Color
    0.06
    ―
    0.06
    Keeping
    0.06
    -St
    0.06
     oa
    0.06
     випад
    0.06
    .=
    0.06
    ＞
    0.06
    formace
    0.06
    Act Density 0.050%

    No Known Activations