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

    Neuronpedia

    INDEX
    Explanations

    model widely available

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amian
    0.39
    PAL
    0.38
    Pal
    0.37
    Robert
    0.36
    Lam
    0.36
    結晶
    0.36
    蘇
    0.35
     trab
    0.35
    觕
    0.35
    myTransform
    0.34
    POSITIVE LOGITS
     Buckeye
    0.40
    lever
    0.39
     leveraged
    0.39
     bucket
    0.38
     Ky
    0.38
     Ivy
    0.38
     lever
    0.38
    λευ
    0.38
     Rewrite
    0.38
    рена
    0.38
    Act Density 0.008%

    No Known Activations