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

    Neuronpedia

    INDEX
    Explanations

    last resort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    早速
    1.02
    ietta
    0.86
    others
    0.85
    दारी
    0.85
    ит
    0.82
    asionally
    0.82
     zunächst
    0.82
     Sweater
    0.80
    INES
    0.78
    ines
    0.76
    POSITIVE LOGITS
     gasp
    1.42
     resort
    1.39
     bastion
    1.37
     resorts
    1.37
     hur
    1.30
     vestiges
    1.26
     ditch
    1.26
    minute
    1.26
    onbury
    1.20
     minute
    1.14
    Act Density 0.059%

    No Known Activations