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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas or equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ккей
    0.58
    en
    0.57
    anwhile
    0.56
    িক
    0.56
    મ
    0.56
    ából
    0.55
    enya
    0.54
     काढ
    0.53
     kræ
    0.52
     moldings
    0.52
    POSITIVE LOGITS
    년간
    0.58
    یعنی
    0.58
     년
    0.57
    comma
    0.56
     years
    0.55
    }$,
    0.54
     ACR
    0.54
    GOB
    0.53
    copter
    0.53
    er
    0.53
    Act Density 0.551%

    No Known Activations