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

    Neuronpedia

    INDEX
    Explanations

    crisis support texts and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Việt
    0.70
     variables
    0.68
     Mut
    0.67
     matrix
    0.66
    िकेट
    0.65
     matrices
    0.64
     Arth
    0.64
     matriz
    0.64
     Variablen
    0.63
     mother
    0.63
    POSITIVE LOGITS
    矨
    0.72
    சாமி
    0.67
    iseen
    0.62
    வரி
    0.61
     gezien
    0.61
    <0x8B>
    0.59
    IW
    0.59
    गन
    0.59
    로우
    0.59
    Firm
    0.58
    Act Density 0.032%

    No Known Activations