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

    Neuronpedia

    INDEX
    Explanations

    features and characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kısm
    0.86
     concerns
    0.85
     tweaks
    0.82
     caveats
    0.81
     considerations
    0.79
     specifics
    0.76
     issues
    0.76
     suggestions
    0.75
     possibilities
    0.73
     fears
    0.73
    POSITIVE LOGITS
     Un
    0.72
    Rescue
    0.69
     Unified
    0.69
    ujudkan
    0.69
     unbroken
    0.68
    ulli
    0.68
    Pocket
    0.67
    Un
    0.66
     परिष
    0.66
     définition
    0.65
    Act Density 0.228%

    No Known Activations