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

    Neuronpedia

    INDEX
    Explanations

    romantic relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DEA
    -0.07
    ництво
    -0.06
    _np
    -0.06
                                 ↵
    -0.06
    IDA
    -0.06
    [@"
    -0.06
    —"
    -0.06
    τού
    -0.06
     informal
    -0.06
     MIDI
    -0.06
    POSITIVE LOGITS
    一样
    0.06
     ขนาด
    0.06
     放
    0.06
     내
    0.06
    .controllers
    0.06
    '],['
    0.06
    -ret
    0.06
    expr
    0.06
     이전
    0.06
    рег
    0.06
    Act Density 0.101%

    No Known Activations