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

    Neuronpedia

    INDEX
    Explanations

    specific contexts and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bank
    0.44
             
    0.42
    ad
    0.42
    add
    0.41
    adm
    0.41
    excell
    0.41
    ﻂ
    0.41
     add
    0.40
     sign
    0.40
                       
    0.40
    POSITIVE LOGITS
    θέ
    0.48
    ကိုယ်
    0.47
     таксама
    0.47
    俠
    0.47
    ρεία
    0.46
     பெரும்பாலான
    0.46
    লেট
    0.45
    ികള്‍
    0.45
     també
    0.45
     細胞
    0.45
    Act Density 0.000%

    No Known Activations