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

    Neuronpedia

    INDEX
    Explanations

    character selection Isolation calibration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     popOperand
    0.61
     compon
    0.46
     wyra
    0.46
     comprendere
    0.45
     expresión
    0.45
     imaginary
    0.44
     esprim
    0.44
     fondamental
    0.43
     visualizing
    0.42
    ayı
    0.42
    POSITIVE LOGITS
    IMO
    0.49
    AVE
    0.49
    KINS
    0.48
    Freedom
    0.47
    Buenas
    0.46
    Alfa
    0.46
    KS
    0.46
    Fi
    0.46
    Kind
    0.46
    Kot
    0.46
    Act Density 0.001%

    No Known Activations