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

    Neuronpedia

    INDEX
    Explanations

    advice specific to situation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不喜欢
    0.44
     среди
    0.41
     parmi
    0.40
    Preferred
    0.39
    iamine
    0.37
     চিকিৎ
    0.37
    いている
    0.37
    럿
    0.36
    Kv
    0.36
     théra
    0.36
    POSITIVE LOGITS
     specific
    0.85
    specific
    0.72
     Specific
    0.69
     spezif
    0.67
    Specific
    0.66
     specifico
    0.65
     конкре
    0.63
     específicos
    0.63
     específico
    0.62
     específica
    0.61
    Act Density 0.000%

    No Known Activations