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

    Neuronpedia

    INDEX
    Explanations

    improving daily feedback

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pesar
    0.54
    핑크
    0.53
    尃
    0.53
     especializada
    0.52
    甴
    0.50
     Validación
    0.50
    χ
    0.49
    잃
    0.48
     effetti
    0.48
    ઝ
    0.48
    POSITIVE LOGITS
    house
    0.53
     pantry
    0.49
    u
    0.48
    oters
    0.45
    ied
    0.43
    inte
    0.43
     houseboat
    0.43
    ilir
    0.42
    work
    0.42
    outs
    0.42
    Act Density 0.000%

    No Known Activations