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

    Neuronpedia

    INDEX
    Explanations

    references to the word "harsh" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    harsh circumstances or criticism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ResumeLayout
    -0.40
    StoryboardSegue
    -0.39
     Slip
    -0.37
    AppComponent
    -0.35
    </table>
    -0.34
     apunta
    -0.33
    expect
    -0.33
    躇
    -0.32
     đạt
    -0.32
     tabung
    -0.32
    POSITIVE LOGITS
    Harsh
    0.72
     TextInputType
    0.68
     Harsh
    0.68
     realities
    0.59
     dureza
    0.59
     harsh
    0.58
    ValueStyle
    0.57
     فريبيس
    0.57
    AnimationsModule
    0.56
    JvmStatic
    0.54
    Act Density 0.005%

    No Known Activations