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

    Neuronpedia

    INDEX
    Explanations

    model responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     కీలక
    0.47
     괜찮
    0.46
    <0xCD>
    0.46
    ͗
    0.45
    犃
    0.44
    GLISH
    0.42
    𝙜
    0.42
     పొ
    0.41
    㝢
    0.41
     ר
    0.41
    POSITIVE LOGITS
    Lak
    0.42
     flick
    0.41
     junk
    0.40
    Boolean
    0.39
     bass
    0.38
     flicks
    0.38
     once
    0.37
     variously
    0.37
     massive
    0.37
    “
    0.37
    Act Density 0.001%

    No Known Activations