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

    Neuronpedia

    INDEX
    Explanations

    electrical current, heating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gazet
    -0.08
     quirky
    -0.08
    ィ
    -0.08
     ymin
    -0.08
     Rak
    -0.07
     kommenden
    -0.07
     cucumber
    -0.07
     blossom
    -0.07
     Optional
    -0.07
     ontbreken
    -0.07
    POSITIVE LOGITS
     heating
    0.14
     Heating
    0.13
    Heating
    0.12
    _heat
    0.10
     calor
    0.10
     overheating
    0.10
     heated
    0.10
     generating
    0.10
    热
    0.10
     heats
    0.10
    Act Density 0.010%

    No Known Activations