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

    Neuronpedia

    INDEX
    Explanations

    lost or forgotten things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     શાંત
    0.42
     paheli
    0.42
    FFA
    0.42
    deload
    0.40
     determinants
    0.40
     purification
    0.37
    দের
    0.37
    abola
    0.37
    改めて
    0.37
    сня
    0.36
    POSITIVE LOGITS
     lymph
    0.50
     adher
    0.50
     adhered
    0.49
     mindestens
    0.45
     dù
    0.45
    minLength
    0.44
     meski
    0.44
     effected
    0.43
     لە
    0.43
     इंग्लंड
    0.42
    Act Density 0.026%

    No Known Activations