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

    Neuronpedia

    INDEX
    Explanations

    human rights and history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gur
    0.78
     улица
    0.71
     получают
    0.71
    yourself
    0.70
     поговорим
    0.70
     hydroph
    0.69
     représentent
    0.68
     넣어
    0.67
     FOREIGN
    0.66
    闩
    0.66
    POSITIVE LOGITS
     beings
    1.25
    oids
    1.01
    oid
    0.98
    istic
    0.86
    历史上
    0.85
    ely
    0.85
    itas
    0.84
    bein
    0.84
    oiden
    0.83
    ELY
    0.82
    Act Density 0.084%

    No Known Activations