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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arel
    -0.07
    StatusBar
    -0.07
     detox
    -0.06
    าซ
    -0.06
    amaz
    -0.06
     datasource
    -0.06
     orch
    -0.06
    oth
    -0.06
    Hint
    -0.06
     Commands
    -0.06
    POSITIVE LOGITS
     chó
    0.07
    .Promise
    0.07
     Vlad
    0.07
    assemble
    0.07
     немає
    0.06
     lever
    0.06
    ."','".$
    0.06
     The
    0.06
     защ
    0.06
     таке
    0.06
    Act Density 0.161%

    No Known Activations