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

    Neuronpedia

    INDEX
    Explanations

    daily activities and plans

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ...'
    0.38
    '){
    0.36
    𝒃
    0.33
     സ്‌
    0.33
    𝖾
    0.33
    ･
    0.32
    '''
    0.32
     Coordin
    0.32
    𝒆
    0.32
    ﺷ
    0.32
    POSITIVE LOGITS
     want
    0.49
     quickly
    0.47
     Want
    0.46
     undertake
    0.46
     माध्यमातून
    0.45
     toward
    0.45
     সঙ্গে
    0.45
     undertook
    0.44
     give
    0.44
     gave
    0.43
    Act Density 0.002%

    No Known Activations