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

    Neuronpedia

    INDEX
    Explanations

    #define and look

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hormati
    0.53
     переменных
    0.51
     tratar
    0.50
     experto
    0.50
     contextos
    0.50
     relación
    0.49
     comparação
    0.49
     necessidade
    0.49
     indoct
    0.49
    破碎
    0.48
    POSITIVE LOGITS
    ton
    0.51
    tron
    0.50
    poch
    0.50
    semble
    0.47
    tons
    0.46
    rl
    0.46
    tní
    0.46
    tains
    0.46
    time
    0.46
     Danke
    0.46
    Act Density 0.000%

    No Known Activations