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

    Neuronpedia

    INDEX
    Explanations

    kidnap abduction Jane Blunt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FOR
    0.48
    ❻
    0.43
    HANG
    0.42
    Loose
    0.40
    श्व
    0.40
    崧
    0.39
    শ্ব
    0.39
    Tout
    0.39
    SSH
    0.38
     setShow
    0.38
    POSITIVE LOGITS
    jane
    0.65
     Blunt
    0.61
     blunt
    0.60
     Jane
    0.59
     kidnapped
    0.59
     kidnap
    0.56
    bl
    0.54
     abduction
    0.54
    Jane
    0.53
     bl
    0.53
    Act Density 0.000%

    No Known Activations